Live briefing
Everything about Normalization (machine learning)
Machine learning technique
In machine learning, normalization is a statistical technique with various applications. There are two main forms of normalization, namely data normalization and activation normalization. Data normalization includes methods that rescale input data so that the features have the same range, mean, variance, or other statistical properties. For instance, a popular choice of feature scaling method is min-max normalization, where each feature is transformed to have the same range. This solves the problem of different features having vastly different scales, for example if one feature is measured in kilometers and another in nanometers. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Normalization (machine learning)A 5-minute orientation
- Skim a recent paper: Robustness of machine learning to color, size change, normalization, and image enhancement on micrograph datasets with large sample differencesInfluential work since 2022
- Pick up a classic book: Fishing LogThe most-reprinted book on the subject
- Read the landmark paper: When to Use Standardization and Normalization: Empirical Evidence From Machine Learning Models and XAICited 148 times
- Go sideways: Batch normalizationA closely related topic
- Go sideways: Weight initializationA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🏆 Landmark papers (most cited)
When to Use Standardization and Normalization: Empirical Evidence From Machine Learning Models and XAI
Cross-platform normalization of microarray and RNA-seq data for machine learning applications
Subject-independent hand gesture recognition using normalization and machine learning algorithms
An Agile Approach to Identify Single and Hybrid Normalization for Enhancing Machine Learning-Based Network Intrusion Detection
Cross-platform normalization enables machine learning model training on microarray and RNA-seq data simultaneously
Data normalization in machine learning
An intercomparison of weather normalization of PM2.5 concentration using traditional statistical methods, machine learning, and chemistry transport models
Extending life cycle assessment normalization factors and use of machine learning – A Slovenian case study
🆕 Influential since 2022
Robustness of machine learning to color, size change, normalization, and image enhancement on micrograph datasets with large sample differences
Sliding-Window Normalization to Improve the Performance of Machine-Learning Models for Real-Time Motion Prediction Using Electromyography
Slower than expected reduction in annual PM2.5 in Xi'an revealed by machine learning-based meteorological normalization
An Investigation on Disparity Responds of Machine Learning Algorithms to Data Normalization Method
Machine Learning and Meteorological Normalization for Assessment of Particulate Matter Changes during the COVID-19 Lockdown in Zagreb, Croatia
📚 Books worth reading
- 📕Fishing LogHarold RIVERA · 2022
Intelligence BulletinUnited States. War Department. Military Intelligence Service · 1942
Neural Information ProcessingTingwen Huang · 2012
What we hear in musicAnne Faulkner Oberndorfer · 1913
Language AcquisitionMaria Teresa Guasti · 2002
Probability, random processes, and statistical analysisHisashi Kobayashi · 2011- 📕The Cambridge handbook of psycholinguisticsMichael Spivey · 2012
Handbook of functional MRI data analysisRussell Alan Poldrack · 2011
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Batch normalization In artificial neural networks, batch normalization (also known as batch norm) is a normalization technique used to make training faster and more stable…
- Weight initialization In deep learning, weight initialization or parameter initialization describes the initial step in creating a neural network. A neural network contains…
- Transformer (deep learning) In deep learning, the transformer is a family of artificial neural network architectures based on the multi-head attention mechanism, in which input data…
- Residual neural network A residual neural network (also referred to as a residual network or ResNet) is a deep learning architecture in which the layers learn residual functions…
- Pooling layer In neural networks, a pooling layer is a kind of network layer that downsamples and aggregates information that is dispersed among many vectors into fewer…
- Vision transformer A vision transformer (ViT) is a transformer designed for computer vision. A ViT decomposes an input image into a series of patches (rather than text into…
- Neural network Gaussian process A Neural Network Gaussian Process (NNGP) is a Gaussian process (GP) obtained as the limit of a certain type of sequence of neural networks. Specifically…
- Vanishing gradient problem In machine learning, the vanishing gradient problem is the problem of greatly diverging gradient magnitudes between earlier and later layers encountered…